Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 173 for “"open world"”.
-
OPEN-WORLD VIDEO STREAM FINGERPRINTING
… approach in larger and more realistic open-world scenarios, followed by a variety of more advanced techniques drawn from the literature on open set recognition, out-of-distribution detection, and robustness to adversarial examples. Our contributions include the dataset and a number of …
-
Towards open-world image recognition
… to achieve models that perform well in the real world, we must overcome the shift from training to real-world data, which involves two factors: (1) covariate shift and (2) unseen classes. Covariate shift occurs when the input distribution of a particular category changes from the training time. …
-
Toward Open World Visual Understanding
Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2024
-
Evaluation of Open-World Learning Systems
… and promptly to prevent undesirable outcomes. Open-world learning (OWL) is a research field aimed at addressing this challenge by enabling AI systems to detect and adapt to novel situations. However, progress in OWL requires the development of AI systems with this capability, alongside …
-
Constraint-Driven Open-World Scene Generation
We introduce an alternative method for open-world scene generation. In this thesis, Graph-based Wave Function Collapse (GWFC) is integrated with Space Colonization Algorithm (SCA) and used to place objects in an unstructured 3D environment. This combined algorithm, Space Colonization Graph-based …
-
Learning for open-world mobile robots
… original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Towards open world semi supervised detection
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-05-01
-
AI for an open world game
This project revolves around simulating a small society primarily meant for video game usage. We focused on making the experience unique from other video game civilian simulations. Especially when it comes to body language, unique personalities and interactions with other actors. Another big part …
-
Towards Open World Graph Learning and Applications
… networks has largely been built upon closed-world assumptions that fundamentally mischaracterize real-world applications: graphs evolve continuously across multiple timescales, exhibit heterogeneous structures that connect dissimilar entities through heterophilic relationships, contain …
-
Efficient sensorimotor learning for open-world robot manipulation
… new scenarios. This dissertation considers Open-world Robot Manipulation, a manipulation problem where a robot must generalize or quickly adapt to new objects, scenes, or tasks for which it has not been pre-programmed or pre-trained. This dissertation tackles the problem using a methodology …
-
Open-world Machine Learning with Limited Labeled Data
… core abilities to learn new concepts in an open world without access to a massive amount of curated labeled data. Specifically, it addresses several key problems such as learning with limited labeled data, incremental data, unlabeled data, and imbalanced and noisy data. The algorithms …
-
General supervised learning framework for open world classification
… does not contain all classes is referred to as open-world classification problem. Hence, when the model is applied to new data, it is imperative to identify the instances belonging to unknown classes. While literature addresses this issue, most of the work in this field has been limited to the …
-
Solving Visual Species Recognition with Open-World Resources
… of "data scarcity" in few-shot VSR, we exploit open-world resources, including (1) the open-world models, such as the Vision-Language Models (VLMs), e.g., CLIP, and Vision Foundation Models (VFMs), e.g., DINOv2; (2) open-world data, e.g., VLMs' publicly available pretraining data; (3) existing …
-
Solving Visual Species Recognition with Open-World Resources
… of "data scarcity" in few-shot VSR, we exploit open-world resources, including (1) the open-world models, such as the Vision-Language Models (VLMs), e.g., CLIP, and Vision Foundation Models (VFMs), e.g., DINOv2; (2) open-world data, e.g., VLMs' publicly available pretraining data; (3) existing …
-
Open-world deep learning applied to pollen detection
… original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
What Can Heritage Professionals Learn from Open World Games?
What can real-world cultural heritage sites learn from the video games industry about presenting a coherent story, while giving visitors freedom to explore and allowing them to become participants in the story-making? How do cultural heritage professionals have to change their storytelling …
-
Recognizing New Visual Categories in Real Open World Environments
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Grounding and Generating 4D Humans in the Open World
… humans as physical agents in the physical world. Yet, current human analysis in the wild largely focuses on visual reconstruction: the alignment of a 3D mesh to 2D pixels. While foundational, this approach is limited: it fails to ground reconstructions in a coherent physical space, and …
Page 1 of 9